SCEF: A Support-Confidence-aware Embedding Framework for Knowledge Graph Refinement
This work addresses the limitation of existing KG embedding models that ignore error detection, offering a more comprehensive solution for applications relying on accurate knowledge graphs, though it is incremental in combining internal and external evidence.
The authors tackled the problem of knowledge graph refinement by proposing SCEF, a framework that simultaneously handles completion and error detection, achieving improved performance on real-world datasets with concrete gains in metrics like Hits@10 and MRR.
Knowledge graph (KG) refinement mainly aims at KG completion and correction (i.e., error detection). However, most conventional KG embedding models only focus on KG completion with an unreasonable assumption that all facts in KG hold without noises, ignoring error detection which also should be significant and essential for KG refinement.In this paper, we propose a novel support-confidence-aware KG embedding framework (SCEF), which implements KG completion and correction simultaneously by learning knowledge representations with both triple support and triple confidence. Specifically, we build model energy function by incorporating conventional translation-based model with support and confidence. To make our triple support-confidence more sufficient and robust, we not only consider the internal structural information in KG, studying the approximate relation entailment as triple confidence constraints, but also the external textual evidence, proposing two kinds of triple supports with entity types and descriptions respectively.Through extensive experiments on real-world datasets, we demonstrate SCEF's effectiveness.